Mirror EmbeddingGemma 2 text-embedding ONNX models and tokenizer

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+pipeline_tag: feature-extraction
+library_name: onnx
+base_model:
+- google/embeddinggemma-2
+tags:
+- embedding
+- feature-extraction
+- sentence-similarity
+- onnx
+- text-embeddings-inference
+language:
+- multilingual
+---
+
+# EmbeddingGemma 2 — text embedding ONNX mirror
+
+Text-embedding subset of [EmbeddingGemma 2](https://huggingface.co/google/embeddinggemma-2)
+by Google DeepMind, mirrored for on-device use with
+[`lib_onnx`](https://pub.dev/packages/lib_onnx) (ONNX Runtime for Dart/Flutter).
+
+Files are unmodified copies of:
+
+| Files | Source | Revision |
+|---|---|---|
+| `onnx/model*.onnx`, `onnx/model*.onnx_data`, `config.json`, `config_sentence_transformers.json`, `tokenizer.json`, `tokenizer_config.json` | [onnx-community/embeddinggemma-2-ONNX](https://huggingface.co/onnx-community/embeddinggemma-2-ONNX) | `daa72c51243991dfcaf9f9137d2c573d8f7790c0` |
+| `tokenizer.model` (SentencePiece) | [google/embeddinggemma-2](https://huggingface.co/google/embeddinggemma-2) | `f9972ac22e696a105c482202646979e33e4b5a1e` |
+
+The vision and audio encoders are not mirrored. License: Apache 2.0, as published
+by the upstream repositories ([Gemma license](https://ai.google.dev/gemma/docs/gemma_4_license)).
+
+## Model contract
+
+| Input | Type | Shape | Text-only value |
+|---|---|---|---|
+| `input_ids` | int64 | `[batch, sequence]` | Gemma tokenizer ids |
+| `attention_mask` | int64 | `[batch, sequence]` | 1 for tokens, 0 for padding |
+| `image_features` | float32 | `[num_image_tokens, 512]` | empty `[0, 512]` |
+| `video_features` | float32 | `[num_video_tokens, 512]` | empty `[0, 512]` |
+| `audio_features` | float32 | `[num_audio_tokens, 512]` | empty `[0, 512]` |
+
+| Output | Shape | Meaning |
+|---|---|---|
+| `sentence_embedding` | `[batch, 768]` | pooled, projected embedding (L2-normalize before cosine/dot) |
+| `last_hidden_state` | `[batch, sequence, 768]` | per-token states |
+
+Matryoshka truncation to 512, 256 or 128 dimensions is supported: keep the
+leading dimensions and re-normalize.
+
+Prefix text inputs with a task instruction:
+
+- query: `task: search result | query: {text}`
+- document: `title: {title or none} | text: {text}`
+- symmetric tasks: `task: sentence similarity | query: {text}` (also `classification`, `clustering`)
+
+## Variants
+
+| File | Precision | Size (data) |
+|---|---|---|
+| `onnx/model_q4f16.onnx` | 4-bit weights, fp16 | 157 MB |
+| `onnx/model_q4.onnx` | 4-bit weights | 174 MB |
+| `onnx/model_quantized.onnx` | int8 | 314 MB |
+| `onnx/model_fp16.onnx` | fp16 | 542 MB |
+| `onnx/model.onnx` | fp32 | 1.08 GB |
+
+Each `.onnx` graph loads its `.onnx_data` external-data file from the same directory.
+
+## SHA-256
+
+```
+4d777ef5bdc1aa36227abdfb77c3e49e7b9c892d16e1b6bda41c393504828be4  tokenizer.json
+e594c8a90eb08d8bda498ff4747977dc827ae0c3c56b5c0d41a605a22d02ef03  tokenizer.model
+a49e227d7e0e5f4ee606d79879d084264366367bc6318f344ab179e35d4fd6a4  onnx/model_fp16.onnx
+b9dbe09415d77c8686ba6e216a244086f4ada1608238c13f2bfaa587ba627207  onnx/model_fp16.onnx_data
+f9eeba97acddf139b8ee2ddf04bc30dceafa88de93fadf74d7644e0d61a477a9  onnx/model_q4.onnx
+c3975f2d1ab7a1878ae31a7d7a9b7804a827aff3800b60dfceafce21cac3df49  onnx/model_q4.onnx_data
+53feeced79582d661e30adeaa9829cea90d92b1c78347e26fd123773580f71d0  onnx/model_q4f16.onnx
+c39fbaa1fb4221f04beb82786a06b81999c514fd39e84fcd58ef79413c87fa56  onnx/model_q4f16.onnx_data
+d06edd601f851c633a2519304cbeb8dc6170d7ceb61b436625c17fb9b6e74953  onnx/model_quantized.onnx
+278a7ff1248c3618e4bd11a607fc54f7bdc7778854230f3956d3f86bd9db4f3b  onnx/model_quantized.onnx_data
+bc47de15f81208a5c99e5ab10f746d5e33b51ea228b7dc0bef9c133a94f1c1c3  onnx/model.onnx
+9fd452bfc6916e5a92f080f8dada35598ca4512b21c65897d4c5974d5f9630a2  onnx/model.onnx_data
+```

config.json

@@ -0,0 +1,196 @@
+{
+  "architectures": [
+    "EmbeddingGemma2Model"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "embedding_gemma2",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "embedding_dim": 768,
+    "eos_token_id": 1,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 512,
+    "hidden_size_per_layer_input": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "embedding_gemma2_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": 0,
+    "per_layer_config": {
+      "05": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "11": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "17": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "23": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "vocab_size": 262144
+  },
+  "transformers_version": "5.18.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "axial"
+    },
+    "standardize": false,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "audio_encoder.onnx": 1,
+      "audio_encoder_fp16.onnx": 1,
+      "audio_encoder_q4.onnx": 1,
+      "audio_encoder_q4f16.onnx": 1,
+      "audio_encoder_quantized.onnx": 1,
+      "model.onnx": 1,
+      "model_fp16.onnx": 1,
+      "model_q4.onnx": 1,
+      "model_q4f16.onnx": 1,
+      "model_quantized.onnx": 1,
+      "vision_encoder.onnx": 1,
+      "vision_encoder_fp16.onnx": 1,
+      "vision_encoder_q4.onnx": 1,
+      "vision_encoder_q4f16.onnx": 1,
+      "vision_encoder_quantized.onnx": 1
+    }
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,38 @@
+{
+  "__version__": {
+    "pytorch": "2.14.0+cu130",
+    "sentence_transformers": "6.1.0",
+    "transformers": "5.18.0.dev0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "BitextMining": "task: search result | query: ",
+    "Classification": "task: classification | query: ",
+    "Clustering": "task: clustering | query: ",
+    "CodeRetrieval": "task: code retrieval | query: ",
+    "Document": "title: none | text: ",
+    "FactChecking": "task: fact checking | query: ",
+    "InstructionRetrieval": "task: code retrieval | query: ",
+    "MultilabelClassification": "task: classification | query: ",
+    "PairClassification": "task: sentence similarity | query: ",
+    "QuestionAnswering": "task: question answering | query: ",
+    "Reranking": "task: search result | query: ",
+    "Retrieval": "task: search result | query: ",
+    "Retrieval-document": "title: none | text: ",
+    "Retrieval-query": "task: search result | query: ",
+    "STS": "task: sentence similarity | query: ",
+    "SearchQuery": "task: search result | query: ",
+    "SentenceSimilarity": "task: sentence similarity | query: ",
+    "Summarization": "task: sentence similarity | query: ",
+    "document": "title: none | text: ",
+    "query": "task: search result | query: "
+  },
+  "requirements": {
+    "sentence-transformers": {
+      "reason": "Older versions ignore the order of multimodal dict inputs and cannot put several images or texts into a single embedding.",
+      "specifier": ">=6.1.0"
+    }
+  },
+  "similarity_fn_name": "cosine"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc47de15f81208a5c99e5ab10f746d5e33b51ea228b7dc0bef9c133a94f1c1c3
+size 421421

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd452bfc6916e5a92f080f8dada35598ca4512b21c65897d4c5974d5f9630a2
+size 1084170240

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49e227d7e0e5f4ee606d79879d084264366367bc6318f344ab179e35d4fd6a4
+size 425780

onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9dbe09415d77c8686ba6e216a244086f4ada1608238c13f2bfaa587ba627207
+size 542085120

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9eeba97acddf139b8ee2ddf04bc30dceafa88de93fadf74d7644e0d61a477a9
+size 490742

onnx/model_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3975f2d1ab7a1878ae31a7d7a9b7804a827aff3800b60dfceafce21cac3df49
+size 174028800

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53feeced79582d661e30adeaa9829cea90d92b1c78347e26fd123773580f71d0
+size 495298

onnx/model_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39fbaa1fb4221f04beb82786a06b81999c514fd39e84fcd58ef79413c87fa56
+size 156862464

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06edd601f851c633a2519304cbeb8dc6170d7ceb61b436625c17fb9b6e74953
+size 495165

onnx/model_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278a7ff1248c3618e4bd11a607fc54f7bdc7778854230f3956d3f86bd9db4f3b
+size 313724928

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d777ef5bdc1aa36227abdfb77c3e49e7b9c892d16e1b6bda41c393504828be4
+size 32170510

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e594c8a90eb08d8bda498ff4747977dc827ae0c3c56b5c0d41a605a22d02ef03
+size 4689013

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>",
+    "video_token": "<|video|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "EmbeddingGemma2Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "video_token": "<|video|>"
+}